Inventor

HOFFMEISTER BJORN

US40 patents

⚠️ This page may combine multiple inventors who share the name “HOFFMEISTER BJORN”. Patents are grouped by organization below to help distinguish them — per-person disambiguation is on the roadmap.

HOFFMEISTER BJORN

AMAZON TECH INC

Keyword detection modeling using contextual and environmental information

Low latency and memory efficient keywork spotting

Keyword spotting with competitor models

Stochastic modeling of user interactions with a detection system

Security measures for an electronic device

Language model adaptation

Keyword spotting using multi-task configuration

Error tolerant neural network model compression

Local speech recognition of frequent utterances

Qualifying trigger expressions in speech-based systems

Detecting system-directed speech

Using adaptation data with cloud-based speech recognition

Estimating false rejection rate in a detection system

Acoustic echo cancellation and automatic speech recognition with random noise

Deep multi-channel acoustic modeling using multiple microphone array geometries

Deep multi-channel acoustic modeling

Neural network processing of multiple feature streams using max pooling and restricted connectivity

Anchored speech detection and speech recognition

Markov-based sequence tagging using neural networks

Speech model retrieval in distributed speech recognition systems

Speech detection and speech recognition

Speech recognizer with multi-directional decoding

Monophone-based background modeling for wakeword detection

Device-directed utterance detection

Language model speech endpointing

Low latency and memory efficient keyword spotting

Estimating speaker-specific affine transforms for neural network based speech recognition systems

Speech model retrieval in distributed speech recognition systems

Speech recognition with combined grammar and statistical language models

Wake word detection modeling

Keyword detection modeling using contextual information

Class-based discriminative training of speech models

Deep multi-channel acoustic modeling

Endpointing in speech processing

Device-directed utterance detection

Language model adaptation

Anchored speech detection and speech recognition

Low latency audio processing techniques

RAWLES LLC

Accepting voice commands based on user identity

HOFFMEISTER BJORN

Duration ratio modeling for improved speech recognition